Objective Sudden unexpected death in epilepsy (SUDEP) is the leading cause of epilepsy-related mortality. Although lots of effort has been made in identifying clinical risk factors for SUDEP in the literature, there are few validated methods to predict individual SUDEP risk. Prolonged postictal EEG suppression (PGES) is a potential SUDEP biomarker, but its occurrence is infrequent and requires epilepsy monitoring unit admission. We use machine learning methods to examine SUDEP risk using interictal EEG and ECG recordings from SUDEP cases and matched living epilepsy controls. Methods This multicenter, retrospective, cohort study examined interictal EEG and ECG recordings from 30 SUDEP cases and 58 age-matched living epilepsy patient controls. We trained machine learning models with interictal EEG and ECG features to predict the retrospective SUDEP risk for each patient. We assessed cross-validated classification accuracy and the area under the receiver operating characteristic (AUC) curve. Results The logistic regression (LR) classifier produced the overall best performance, outperforming the support vector machine (SVM), random forest (RF), and convolutional neural network (CNN). Among the 30 patients with SUDEP [14 females; mean age (SD), 31 (8.47) years] and 58 living epilepsy controls [26 females (43%); mean age (SD) 31 (8.5) years], the LR model achieved the median AUC of 0.77 [interquartile range (IQR), 0.73–0.80] in five-fold cross-validation using interictal alpha and low gamma power ratio of the EEG and heart rate variability (HRV) features extracted from the ECG. The LR model achieved the mean AUC of 0.79 in leave-one-center-out prediction. Conclusions Our results support that machine learning-driven models may quantify SUDEP risk for epilepsy patients, future refinements in our model may help predict individualized SUDEP risk and help clinicians correlate predictive scores with the clinical data. Low-cost and noninvasive interictal biomarkers of SUDEP risk may help clinicians to identify high-risk patients and initiate preventive strategies.
more »
« less
Exploring Gut Microbiome in Predicting the Efficacy of Immunotherapy in Non-Small Cell Lung Cancer
We performed various analyses on the taxonomic and functional features of the gut microbiome from NSCLC patients treated with immunotherapy to establish a model that may predict whether a patient will benefit from immunotherapy. We collected 65 published whole metagenome shotgun sequencing samples along with 14 samples from our previous study. We systematically studied the taxonomical characteristics of the dataset and used both the random forest (RF) and the multilayer perceptron (MLP) neural network models to predict patients with progression-free survival (PFS) above 6 months versus those below 3 months. Our results showed that the RF classifier achieved the highest F-score (85.2%) and the area under the receiver operating characteristic curve (AUC) (95%) using the protein families (Pfam) profile, and the MLP neural network classifier achieved a 99.9% F-score and 100% AUC using the same Pfam profile. When applying the model trained in the Pfam profile directly to predict the treatment response, we found that both trained RF and MLP classifiers significantly outperformed the stochastic predictor in F-score. Our results suggested that such a predictive model based on functional (e.g., Pfam) rather than taxonomic profile might be clinically useful to predict whether an NSCLC patient will benefit from immunotherapy, as both the F-score and AUC of functional profile outperform that of taxonomic profile. In addition, our model suggested that interactive biological processes such as methanogenesis, one-carbon, and amino acid metabolism might be important in regulating the immunotherapy response that warrants further investigation.
more »
« less
- Award ID(s):
- 1943291
- NSF-PAR ID:
- 10405429
- Date Published:
- Journal Name:
- Cancers
- Volume:
- 14
- Issue:
- 21
- ISSN:
- 2072-6694
- Page Range / eLocation ID:
- 5401
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Background Predictive models utilizing social determinants of health (SDH), demographic data, and local weather data were trained to predict missed imaging appointments (MIA) among breast imaging patients at the Boston Medical Center (BMC). Patients were characterized by many different variables, including social needs, demographics, imaging utilization, appointment features, and weather conditions on the date of the appointment. Methods This HIPAA compliant retrospective cohort study was IRB approved. Informed consent was waived. After data preprocessing steps, the dataset contained 9,970 patients and 36,606 appointments from 1/1/2015 to 12/31/2019. We identified 57 potentially impactful variables used in the initial prediction model and assessed each patient for MIA. We then developed a parsimonious model via recursive feature elimination, which identified the 25 most predictive variables. We utilized linear and non-linear models including support vector machines (SVM), logistic regression (LR), and random forest (RF) to predict MIA and compared their performance. Results The highest-performing full model is the nonlinear RF, achieving the highest Area Under the ROC Curve (AUC) of 76% and average F1 score of 85%. Models limited to the most predictive variables were able to attain AUC and F1 scores comparable to models with all variables included. The variables most predictive of missed appointments included timing, prior appointment history, referral department of origin, and socioeconomic factors such as household income and access to caregiving services. Conclusions Prediction of MIA with the data available is inherently limited by the complex, multifactorial nature of MIA. However, the algorithms presented achieved acceptable performance and demonstrated that socioeconomic factors were useful predictors of MIA. In contrast with non-modifiable demographic factors, we can address SDH to decrease the incidence of MIA.more » « less
-
more » « less
Background CD8+T cell in pancreatic ductal adenocarcinoma (PDAC) is closely related to the prognosis and treatment response of patients. Accurate preoperative CD8+T‐cell expression can better identify the population benefitting from immunotherapy.
Purpose To develop and validate a machine learning classifier based on noncontrast magnetic resonance imaging (MRI) for the preoperative prediction of CD8+T‐cell expression in patients with PDAC.
Study Type Retrospective cohort study.
Population Overall, 114 patients with PDAC undergoing MR scan and surgical resection; 97 and 47 patients in the training and validation cohorts.
Field Strength/Sequence/3 T Breath‐hold single‐shot fast‐spin echo T2‐weighted sequence and noncontrast T1‐weighted fat‐suppressed sequences.
Assessment CD8+T‐cell expression was quantified using immunohistochemistry. For each patient, 2232 radiomics features were extracted from noncontrast T1‐ and T2‐weighted images and reduced using the Wilcoxon rank‐sum test and least absolute shrinkage and selection operator method. Linear discriminative analysis was used to construct radiomics and mixed models. Model performance was determined by its discriminative ability, calibration, and clinical utility.
Statistical Tests Kaplan–Meier estimates, Student's t‐test, the Kruskal–Wallis H test, and the chi‐square test, receiver operating characteristic curve, and decision curve analysis.
Results A log‐rank test showed that the survival duration in the CD8‐high group (25.51 months) was significantly longer than that in the CD8‐low group (22.92 months). The mixed model included all MRI characteristics and 13 selected radiomics features, and the area under the curve (AUC) was 0.89 (95% confidence interval [CI], 0.77–0.92) and 0.69 (95% CI, 0.53–0.82) in the training and validation cohorts. The radiomics model included 13 radiomics features, which showed good discrimination in the training cohort (AUC, 0.85; 95% CI, 0.77–0.92) and the validation cohort (AUC, 0.76; 95% CI, 0.61–0.87).
Data Conclusions This study developed a noncontrast MRI‐based radiomics model that can preoperatively determine CD8+T‐cell expression in patients with PDAC and potentially immunotherapy planning.
Evidence Level 5
Technical Efficacy Stage 2
-
more » « less
Abstract Timely and accurate referral of end-stage heart failure patients for advanced therapies, including heart transplants and mechanical circulatory support, plays an important role in improving patient outcomes and saving costs. However, the decision-making process is complex, nuanced, and time-consuming, requiring cardiologists with specialized expertise and training in heart failure and transplantation.
In this study, we propose two logistic tensor regression-based models to predict patients with heart failure warranting evaluation for advanced heart failure therapies using irregularly spaced sequential electronic health records at the population and individual levels. The clinical features were collected at the previous visit and the predictions were made at the very beginning of the subsequent visit. Patient-wise ten-fold cross-validation experiments were performed. Standard LTR achieved an average F1 score of 0.708, AUC of 0.903, and AUPRC of 0.836. Personalized LTR obtained an F1 score of 0.670, an AUC of 0.869 and an AUPRC of 0.839. The two models not only outperformed all other machine learning models to which they were compared but also improved the performance and robustness of the other models via weight transfer. The AUPRC scores of support vector machine, random forest, and Naive Bayes are improved by 8.87%, 7.24%, and 11.38%, respectively.
The two models can evaluate the importance of clinical features associated with advanced therapy referral. The five most important medical codes, including chronic kidney disease, hypotension, pulmonary heart disease, mitral regurgitation, and atherosclerotic heart disease, were reviewed and validated with literature and by heart failure cardiologists. Our proposed models effectively utilize EHRs for potential advanced therapies necessity in heart failure patients while explaining the importance of comorbidities and other clinical events. The information learned from trained model training could offer further insight into risk factors contributing to the progression of heart failure at both the population and individual levels.
-
Abstract Non-small-cell lung cancer (NSCLC) represents approximately 80–85% of lung cancer diagnoses and is the leading cause of cancer-related death worldwide. Recent studies indicate that image-based radiomics features from positron emission tomography/computed tomography (PET/CT) images have predictive power for NSCLC outcomes. To this end, easily calculated functional features such as the maximum and the mean of standard uptake value (SUV) and total lesion glycolysis (TLG) are most commonly used for NSCLC prognostication, but their prognostic value remains controversial. Meanwhile, convolutional neural networks (CNN) are rapidly emerging as a new method for cancer image analysis, with significantly enhanced predictive power compared to hand-crafted radiomics features. Here we show that CNNs trained to perform the tumor segmentation task, with no other information than physician contours, identify a rich set of survival-related image features with remarkable prognostic value. In a retrospective study on pre-treatment PET-CT images of 96 NSCLC patients before stereotactic-body radiotherapy (SBRT), we found that the CNN segmentation algorithm (U-Net) trained for tumor segmentation in PET and CT images, contained features having strong correlation with 2- and 5-year overall and disease-specific survivals. The U-Net algorithm has not seen any other clinical information (e.g. survival, age, smoking history, etc.) than the images and the corresponding tumor contours provided by physicians. In addition, we observed the same trend by validating the U-Net features against an extramural data set provided by Stanford Cancer Institute. Furthermore, through visualization of the U-Net, we also found convincing evidence that the regions of metastasis and recurrence appear to match with the regions where the U-Net features identified patterns that predicted higher likelihoods of death. We anticipate our findings will be a starting point for more sophisticated non-intrusive patient specific cancer prognosis determination. For example, the deep learned PET/CT features can not only predict survival but also visualize high-risk regions within or adjacent to the primary tumor and hence potentially impact therapeutic outcomes by optimal selection of therapeutic strategy or first-line therapy adjustment.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.3390/cancers14215401
